CV

Education

• B.S. in Chemistry and Biophysics, Macalester College, 2015
• M.S. in Bioinformatics, ETH Zürich, 2020

Work experience

• 2020: Master Thesis in Protein Language Modeling
  • IBM Research, Cognitive Computing and Industry Solutions
  • Built unsupervised NLP language models (embeddings) for protein sequences
  • Applied NER, neural machine translation, sentiment analysis to protein sequence domain
  • Used embeddings for token-level classification tasks such as protein structure prediction, and sentence-level tasks like protein function prediction
  • Tools used: Pyhton, PyTorch, Git, Huggingface libraries
• Fall 2019: Computer Vision and Natural Language Understanding Intern
  • Novartis Institutes for BioMedical Research (NIBR)
  • Implemented a multimodal learning model to automatically generate text reports from biomedical images (chest X-rays)
  • Adapted established NLP and computer vision models to biomedical domain
  • Wrote a technical report and presented the findings to other Data Science Analytics team
  • Tools used: Python, PyTorch, JupyterHUB, tmux, Git
• 2019: Programming research assistant
  • Decision Science Laboratory (DeSciL), ETH Zürich
  • Developed Django web apps for Behavioral Economics research experiments
  • Participated in meetings with Economics researchers to adjust project design
  • Tools used: Python, Django, JavaScript, CSS, HTML, OTree
• 2016-2017: Bioinformatician
  • Specifica Inc. in Basel and Santa Fe, NM
  • Implemented genomic data query, processing and analytics workflows in R and Unix shell
  • Established sequencing protocol of yeast-phage display selections against disease biomarkers
  • Identified antibody drug candidates with gene annotation and clonotyping algorithms
  • Tools: R, Python, Bash shell, various Bioinformatics libraries
• 2015-2016: Research Assistant at Viral Biophysics Laboratory
  • University of Washington, Seattle
  • Introduced potential HIV-1 envelope-stabilizing mutations with RosettaDesign and MD simulations
  • Contributed to the development of a new antibody-independent HIV Env purification method
  • Modeled HIV-1 Env biophysical stability and dynamics from light scattering, Hydrogen-Deuterium Exchange Mass Spectroscopy and Small-angle X-ray scattering experiments

Skills

• Programming
  • Python
  • R
  • Java (basics)
• Machine Learning
  • PyTorch
  • Scikit-learn
  • HuggingFace libraries
  • AllenNLP
  • Gensim
  • NumPy
• Big data
  • Hadoop framework
  • MySQL
  • HPC and LSF cluster
  • JupyterHub
  • Pandas
• DevOps
  • scripting in Bash and Python
  • Docker config management
  • Git version control
  • Jenkins continuous integration
  • Azure cloud

Publications

Epitope-Independent Purification of Native-Like Envelope Trimers from Diverse HIV-1 Isolates

Verkerke, Hans. (2016). "Epitope-Independent Purification of Native-Like Envelope Trimers from Diverse HIV-1 Isolates " Journal of Virology. 6(1).

Medical Report Generation from Jointly Learned Medical Image and Text Representations

Filipavicius, Modestas et al., (2019). "Medical Report Generation from Jointly Learned Medical Image and Text Representations." NIBR Publications . 12(2).

PaccMannRL on SARS-CoV-2: Designing antiviral candidates with conditional generative models

Born, Jannis et al., (2020). "PaccMannRL on SARS-CoV-2: Designing antiviral candidates with conditional generative models." arXiv2005(13285)

Service and leadership

• Member at Bioinformatics Student Committee (CBB) at ETH Zürich
  • Organized career events for Bioinformatics students, attended VIS meetings,
  • 2018-2020
• Kullu Volunteering Project
  • http://volunteers.uwcrcn.no/kullu-project-northern-india-2
  • Instructed First Aid in local schools in Himachal Pradesh
  • August 2010 - May 2011

Awards

• University of Washington Top Scholar Award (2015)
• HHMI Young Researchers Scholarship (2013)
• Shelby Davis United World College Scholarship (2010)